🐦 Twitter Post Details

Viewing enriched Twitter post

@llama_index

We’re excited to feature a set of novel RAG tips/tricks 💡 from @sisilmehta (@heyjasperai). These tips enabled his team to build a production app, powered by @llama_index, that serves end users! 🔥 Available in a special @llama_index session video 👇. These tips include the following: 1. Sub-document metadata: Adding the right "layers" of metadata; besides global document context, also inject summary context from "sub-documents" to more precisely localize each chunk. 2. Use LLMs to rerank chunk summaries. LLMs are quite good at reranking, but they’re slow the larger the context. Reduce token usage by reranking summaries that reference underlying chunks. 3. Use XML and emotion prompting to get well-structured outputs free of hallucinations. Video: https://t.co/DtqLJV1Idh

Media 1
View on Twitter

📊 Media Metadata

{
  "media": [
    {
      "url": "https://pbs.twimg.com/media/GGooU1yaIAAz0cQ.jpg",
      "type": "photo",
      "original_url": "https://pbs.twimg.com/media/GGooU1yaIAAz0cQ.jpg",
      "format_converted_from_list": true
    }
  ],
  "conversion_date": "2025-08-13T00:32:17.096691",
  "format_converted": true,
  "original_structure": "had_media_only"
}

🔧 Raw API Response

{
  "user": {
    "created_at": "2022-12-18T00:52:44.000Z",
    "default_profile_image": false,
    "description": "The way to connect LLMs to your data.\n\nGithub: https://t.co/HC19j7vMwc\nDocs: https://t.co/QInqg2zksh\nDiscord: https://t.co/3ktq3zzYII\nhttps://t.co/UXeIlwvvbA",
    "fast_followers_count": 0,
    "favourites_count": 1003,
    "followers_count": 55360,
    "friends_count": 21,
    "has_custom_timelines": false,
    "is_translator": false,
    "listed_count": 999,
    "location": "",
    "media_count": 790,
    "name": "LlamaIndex 🦙",
    "normal_followers_count": 55360,
    "possibly_sensitive": false,
    "profile_banner_url": "https://pbs.twimg.com/profile_banners/1604278358296055808/1696908553",
    "profile_image_url_https": "https://pbs.twimg.com/profile_images/1623505166996742144/n-PNQGgd_normal.jpg",
    "screen_name": "llama_index",
    "statuses_count": 2070,
    "translator_type": "none",
    "url": "https://t.co/epzefqQqZx",
    "verified": true,
    "withheld_in_countries": [],
    "id_str": "1604278358296055808"
  },
  "id": "1759263142310527011",
  "conversation_id": "1759263142310527011",
  "full_text": "We’re excited to feature a set of novel RAG tips/tricks 💡 from @sisilmehta (@heyjasperai). These tips enabled his team to build a production app, powered by @llama_index, that serves end users! 🔥\n\nAvailable in a special @llama_index session video 👇. These tips include the following:\n\n1. Sub-document metadata: Adding the right \"layers\" of metadata; besides global document context, also inject summary context from \"sub-documents\" to more precisely localize each chunk.\n\n2. Use LLMs to rerank chunk summaries. LLMs are quite good at reranking, but they’re slow the larger the context. Reduce token usage by reranking summaries that reference underlying chunks.\n\n3. Use XML and emotion prompting to get well-structured outputs free of hallucinations.\n\nVideo: https://t.co/DtqLJV1Idh",
  "reply_count": 3,
  "retweet_count": 45,
  "favorite_count": 262,
  "hashtags": [],
  "symbols": [],
  "user_mentions": [
    {
      "id_str": "217305355",
      "name": "sisil mehta",
      "screen_name": "sisilmehta",
      "profile": "https://twitter.com/sisilmehta"
    },
    {
      "id_str": "1344329647656468481",
      "name": "Jasper",
      "screen_name": "heyjasperai",
      "profile": "https://twitter.com/heyjasperai"
    },
    {
      "id_str": "1604278358296055808",
      "name": "LlamaIndex 🦙",
      "screen_name": "llama_index",
      "profile": "https://twitter.com/llama_index"
    },
    {
      "id_str": "1604278358296055808",
      "name": "LlamaIndex 🦙",
      "screen_name": "llama_index",
      "profile": "https://twitter.com/llama_index"
    }
  ],
  "urls": [],
  "media": [
    {
      "media_url": "https://pbs.twimg.com/media/GGooU1yaIAAz0cQ.jpg",
      "type": "photo"
    }
  ],
  "url": "https://twitter.com/llama_index/status/1759263142310527011",
  "created_at": "2024-02-18T17:06:33.000Z",
  "#sort_index": "1759263142310527011",
  "view_count": 52524,
  "quote_count": 2,
  "is_quote_tweet": false,
  "is_retweet": false,
  "is_pinned": false,
  "is_truncated": true,
  "startUrl": "https://twitter.com/llama_index/status/1759263142310527011"
}